© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1769
    Prev
    Next
    INDEX
    Explanations

    would you like me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    л
    3.89
    an
    3.84
     volna
    3.72
    ➢
    3.49
    र
    2.97
    म
    2.94
    ০
    2.94
     bø
    2.92
     hoses
    2.92
    েন
    2.90
    POSITIVE LOGITS
     potuto
    4.74
    𝚢
    3.72
     fain
    3.65
    𝗯
    3.64
     kunna
    3.54
     putea
    3.52
    ществ
    3.51
     dovuto
    3.51
    𝗶
    3.42
    𝗱
    3.31
    Activations Density 0.201%

    No Known Activations